Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    terms that express ideals, standards, or comparisons regarding quality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Efq
    -1.28
     Jefus
    -1.16
     Majefty
    -1.13
     whoſe
    -1.08
     Theſe
    -1.06
     myſelf
    -1.06
     Monfieur
    -1.03
     Houſe
    -1.03
     pleaſure
    -1.02
     chofe
    -1.00
    POSITIVE LOGITS
    ...
    0.59
     klar
    0.56
     perfect
    0.55
     a
    0.55
    CrossRef
    0.55
    AnchorStyles
    0.55
    parsedMessage
    0.52
    satunya
    0.51
    комен
    0.48
     reccom
    0.46
    Act Density 0.452%

    No Known Activations